Locus says it beat most human teams across live public ML competitions
rohanpaul_ai · x · 2026-08-04
Locus claims the highest peak average rank across live public ML competitions
The post says that across all prize-money competitions with public leaderboards that were live at evaluation time, Locus achieved a higher peak average rank than every other competitor.
The accompanying chart shows Locus outperforming human teams across several competitions, including ROGII, Biohub, ARC-AGI-3, NeuroGolf, AI Agent Security, and ARC-AGI-2, with the share of human teams beaten ranging from 64.5% to 99.2% depending on the benchmark.
The main takeaway is a leaderboard-style claim: Locus is presented as broadly stronger than most human teams across the evaluated contest set.
Related event: Automated System Locus Sets New Post-Training Records(4 posts)→
More from Research
- AI paper argues best-of-K boosts generative expressivity, not just sampling quality — anshulkundaje · 2026-08-04
- ASCII art may be a better taste benchmark for frontier models than you think — weswinder · 2026-08-04
- A curated reading list for DeltaNet, FlashKDA, vLLM serving and MoE — austinvhuang · 2026-08-04
- AI index steepens 5x after late 2024 as compute shifts from pretraining to inference — ProfBuehlerMIT · 2026-08-04
- Free app teaches LLM basics and trains a small model locally on Apple MLX — dr_cintas · 2026-08-04
- Pure VLAs may not need long-horizon planning if VLMs can cover it — m_wulfmeier · 2026-08-04